© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90817
    Prev
    Next
    INDEX
    Explanations

    Assyrians, Vulkan, Vasopressin, Konoha

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     From
    -2.39
    蓠
    -2.39
    ();//
    -2.38
    zieć
    -2.28
    花の
    -2.23
    海军
    -2.22
    з
    -2.22
     While
    -2.16
    蔔
    -2.11
    写真を
    -2.08
    POSITIVE LOGITS
    the
    3.47
    ጺ
    3.28
    1
    2.97
    g
    2.92
     唯美
    2.78
    D
    2.72
    sukienka
    2.70
    婓
    2.69
    ſſer
    2.58
    a
    2.58
    Activations Density 0.159%

    No Known Activations